Skip to main content
Glama
eu-ai-act-scanner

eu-ai-act-scanner

by ark-forge

EU AI Act Compliance Scanner — CLI + MCP Server

PyPI version GitHub Stars Start Free Pro Plan — €29/mo Works with Claude Works with Cursor

One command. Zero config. Full EU AI Act + GDPR compliance report in under 10 seconds.

pip install eu-ai-act-scanner
eu-ai-act-scanner /path/to/your/project

Detects 16 AI frameworks in your codebase, maps each to binding legal articles, returns pass/fail with fix instructions. Free tier, no API key needed.

August 2, 2026 enforcement deadline. Fines up to 35M EUR or 7% global turnover.

If this tool helps your compliance work, a ⭐ on GitHub helps others discover it.

Need audit-grade proof? Certify every scan with ArkForge Trust Layer — tamper-proof, timestamped compliance evidence. 500 free proofs/month.

Get your compliance report →

Quick Start

CLI (scan any project in 10 seconds)

pip install eu-ai-act-scanner   # or: pip install mcp-eu-ai-act
cd your-project/
eu-ai-act-scanner

Output:

========================================================================
  EU AI Act Compliance Scanner
========================================================================

  Files scanned: 42
  AI frameworks detected: 2
    - openai (in 3 files)
    - langchain (in 1 file)

  Risk category: limited
  Compliance score: 4/7 (57%)
  Checks:
    [PASS] Transparency
    [PASS] User Disclosure
    [FAIL] Technical Documentation  → Create docs/TECHNICAL_DOCUMENTATION.md
    [FAIL] Risk Management          → Create docs/RISK_MANAGEMENT.md
    [FAIL] Data Governance          → Create docs/DATA_GOVERNANCE.md

Or specify a path directly: eu-ai-act-scanner /path/to/your/project

Track compliance over time (free): eu-ai-act-scanner . --register you@email.com

Related MCP server: Meridian

Free vs Pro

Free

Pro (€29/mo)

Certified (€99/mo)

Scans per day

5

Unlimited

Unlimited

AI framework detection

✓ (16 frameworks)

✓ (16 frameworks)

✓ (16 frameworks)

Risk category suggestion

✓

✓

✓

Compliance check

—

✓ (content scoring 0-100)

✓

Full compliance report

—

✓ (executive + technical)

✓

Compliance roadmap

—

✓ (week-by-week plan)

✓

Annex IV package

—

✓ (auditor-ready ZIP)

✓

GDPR scan

—

✓

✓

Combined EU AI Act + GDPR

—

✓ (dual-compliance hotspots)

✓

Trust Layer certification

—

—

✓ (cryptographic proof)

CI/CD integration

—

✓

✓

API key

Not required

✓

✓

Tools available

2

10

10 + certification

Free tier: no sign-up, no API key — just pip install and scan. Pro unlocks the full compliance toolkit your team needs before the August 2027 deadline.

→ Compare plans & get your API key

What's New in v2

Feature

Description

generate_compliance_roadmap

Week-by-week action plan to reach compliance before your deadline

generate_annex4_package

Auditor-ready ZIP with all 8 Annex IV sections populated from your code

certify_compliance_report

Cryptographic proof via Trust Layer (EU AI Act Art. 12)

Content scoring

check_compliance now scores document content (0-100), not just existence

Article mapping

Every finding mapped to specific EU AI Act article

MCP Server (from source)

git clone https://github.com/ark-forge/mcp-eu-ai-act.git
cd mcp-eu-ai-act
python3 -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
python3 server.py

Run tests

pip install pytest
pytest tests/ -v

MCP Integration

pip install eu-ai-act-scanner

Claude Code

claude mcp add eu-ai-act -- eu-ai-act-mcp

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "eu-ai-act": {
      "command": "eu-ai-act-mcp"
    }
  }
}

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "eu-ai-act": {
      "command": "eu-ai-act-mcp"
    }
  }
}

HTTP mode (for CI/CD or remote clients)

pip install uvicorn
python3 server.py --http
# Listening on 0.0.0.0:8089

Tools Reference

1. scan_project

Detects AI framework usage in source code and config/manifest files. Supports 16 frameworks across Python, JS, TS, Go, Java, and Rust.

Key parameters: project_path (string, required)

Example output:

{
  "files_scanned": 42,
  "ai_files": [
    {"file": "src/chat.py", "frameworks": ["openai"]},
    {"file": "requirements.txt", "frameworks": ["openai"], "source": "config"}
  ],
  "detected_models": {"openai": ["src/chat.py", "requirements.txt"]}
}

2. check_compliance

Scores document content quality (0-100) and maps each finding to a specific EU AI Act article. Score ≥40 = pass. Fully backward compatible with v1.

Key parameters: project_path (string, required), risk_category (string, default: limited)

Example output (v2):

{
  "risk_category": "high",
  "compliance_score": "4/6",
  "compliance_percentage": 66.7,
  "content_scores": {
    "RISK_MANAGEMENT.md": 82,
    "TRANSPARENCY.md": 45,
    "DATA_GOVERNANCE.md": 12
  },
  "article_map": {
    "art_9": {"status": "pass", "score": 82},
    "art_10": {"status": "fail", "score": 12},
    "art_13": {"status": "pass", "score": 45}
  }
}

3. generate_compliance_roadmap — NEW in v2

Deadline-aware, week-by-week action plan to reach EU AI Act compliance before August 2, 2026. Sequences quick wins first using a criticality × 1/effort algorithm.

Key parameters: project_path (string, required), risk_category (string), target_date (string, ISO format, default: 2027-08-02)

Example output:

{
  "weeks_remaining": 16,
  "phases": [
    {
      "week": 1,
      "action": "Add TRANSPARENCY.md with user disclosure statement",
      "article": "Art. 13",
      "effort_days": 1,
      "priority": "critical"
    },
    {
      "week": 2,
      "action": "Draft risk management procedure covering Art. 9 requirements",
      "article": "Art. 9",
      "effort_days": 3,
      "priority": "high"
    }
  ],
  "estimated_completion_week": 8
}

4. generate_report

Runs scan + compliance check, returns a combined report with two-level output: executive summary for DPO/legal and technical breakdown for developers. Article-by-article citations included.

Key parameters: project_path (string, required), risk_category (string, default: limited)

Example output:

{
  "executive_summary": {
    "compliance_percentage": 67,
    "deadline": "2027-08-02",
    "days_remaining": 117,
    "gap_count": 3,
    "verdict": "Action required — 3 gaps must be addressed before deadline"
  },
  "technical_breakdown": {
    "art_9": {"status": "fail", "missing": ["hazard identification section", "residual risk log"]},
    "art_13": {"status": "pass", "score": 78}
  },
  "recommendations": [
    {"article": "Art. 9", "action": "Add hazard identification section to RISK_MANAGEMENT.md", "effort": "2 days"}
  ]
}

5. suggest_risk_category

Classifies your AI system into an EU AI Act risk category from a plain-text description. Matches against Art. 5 (prohibited), Annex III (high-risk), Art. 52 (limited), and minimal.

Key parameters: system_description (string, required)

Example output:

{
  "suggested_category": "high",
  "confidence": "high",
  "matched_criteria": ["Annex III, Category 4 — AI in employment decisions"],
  "obligations_summary": "Technical documentation, risk management, human oversight, data governance, transparency"
}

6. generate_compliance_templates

Returns starter markdown templates for each required compliance document. Save them in docs/ and fill in the bracketed sections.

Key parameters: risk_category (string, default: high)

For high risk: Risk Management (Art. 9), Technical Documentation (Art. 11), Data Governance (Art. 10), Human Oversight (Art. 14), Robustness (Art. 15), Transparency (Art. 13).


7. generate_annex4_package — NEW in v2

Generates an auditor-ready ZIP with all 8 Annex IV sections populated from your actual project files. Optionally certifies with Trust Layer for cryptographic proof.

Key parameters: project_path (string, required), sign_with_trust_layer (bool, default: false), trust_layer_key (string, optional)

Example output:

{
  "package_path": "/tmp/annex4_myproject_20260407.zip",
  "sha256": "a3f8c2d1...",
  "sections_populated": 8,
  "sections_missing_data": ["section_6_accuracy_metrics"],
  "proof_id": "prf_01j9z8x7w6v5u4t3s2r1",
  "verification_url": "https://trust.arkforge.tech/verify/prf_01j9z8x7w6v5u4t3s2r1"
}

8. certify_compliance_report — NEW in v2

Certifies any compliance report with ArkForge Trust Layer. Returns a tamper-proof proof_id and public verification URL for your auditor (EU AI Act Art. 12 audit trail).

Key parameters: report_data (string, JSON-serialized report), trust_layer_key (string, required)

Example output:

{
  "proof_id": "prf_01j9z8x7w6v5u4t3s2r1",
  "timestamp": "2026-04-07T14:32:00Z",
  "sha256": "a3f8c2d1e4b5...",
  "verification_url": "https://trust.arkforge.tech/verify/prf_01j9z8x7w6v5u4t3s2r1",
  "article": "EU AI Act Art. 12"
}

9. gdpr_scan_project

Scans for personal data processing patterns: PII fields, tracking pixels, geolocation, file uploads, cookie patterns. Maps to GDPR Art. 22/35 requirements.

Key parameters: project_path (string, required)


10. combined_compliance_report

Runs GDPR + EU AI Act scans simultaneously and identifies dual-compliance hotspots — files where both regulations apply at once.

Key parameters: project_path (string, required), risk_category (string, default: limited)

Example output:

{
  "hotspots": [
    {
      "file": "src/hiring_model.py",
      "eu_ai_act_risk": "high",
      "gdpr_risk": "high",
      "overlap_patterns": ["AI+PII", "AI+automated_decision"],
      "combined_articles": ["EU AI Act Art. 14", "GDPR Art. 22"],
      "priority": "critical"
    }
  ],
  "key_insight": "2 files require simultaneous GDPR + EU AI Act remediation"
}

Certify Your Compliance (EU AI Act Art. 12)

The only MCP that generates cryptographically certified compliance evidence.

# Step 1: Generate Annex IV package and certify it
generate_annex4_package(
    project_path="/path/to/project",
    sign_with_trust_layer=True,
    trust_layer_key="your_trust_layer_key"
)
# → Returns proof_id + public verification URL for your auditor

# Step 2: Or certify any compliance report directly
certify_compliance_report(
    report_data='{"compliance_percentage": 87, "risk_category": "high"}',
    trust_layer_key="your_trust_layer_key"
)

Free Trust Layer account: 500 certified proofs/month → arkforge.tech

Pricing

Plan

Price

Includes

Free

€0

5 scans/day · scan_project + suggest_risk_category

Pro

€29/month

Unlimited scans · all 10 tools · compliance roadmap · Annex IV package

Certified

€99/month

Everything in Pro + Trust Layer certification on every report

Get your API key →

REST API

A separate HTTP API (paywall_api.py) provides rate-limited REST endpoints for CI/CD and external clients.

python3 paywall_api.py
# Listening on 0.0.0.0:8091

Method

Path

Auth

Description

GET

/api/v1/status

None

Service status + your rate limit

GET

/api/usage

None

Current free-tier usage for your IP

POST

/api/v1/scan

Free/Pro

Scan a project for AI frameworks

POST

/api/v1/check-compliance

Free/Pro

Check EU AI Act compliance

POST

/api/v1/generate-report

Free/Pro

Full compliance report

POST

/api/v1/scan-repo

Free (rate-limited)

Scan a public HTTPS Git repo by URL (port 443, public hosts only)

POST

/api/checkout

None

Stripe checkout session

POST

/api/webhook

Stripe sig

Stripe webhook handler

Free tier: 5 scans/day per IP, no sign-up required. Pro tier: Unlimited scans, X-API-Key header. 29 EUR/month via arkforge.tech/pricing.

Example: scan via REST

curl -X POST https://arkforge.tech/mcp/api/v1/scan \
  -H "Content-Type: application/json" \
  -d '{"project_path": "/path/to/your/project"}'

Configuration

For the REST API (Stripe payments, email notifications), create a settings.env:

STRIPE_LIVE_SECRET_KEY=sk_live_...
STRIPE_WEBHOOK_SECRET=whsec_...
TRUST_LAYER_INTERNAL_SECRET=<random-64-char-hex>
SMTP_HOST=ssl0.ovh.net
IMAP_USER=contact@example.com
IMAP_PASSWORD=...

Set SETTINGS_ENV_PATH to the file location (defaults to /opt/claude-ceo/config/settings.env).

Supported Frameworks (16)

Framework

Detection covers

OpenAI

GPT-3.5, GPT-4, GPT-4o, o1, o3, embeddings

Anthropic

Claude (Opus, Sonnet, Haiku)

Google Gemini

Gemini Pro, Ultra, 1.5, 2, 3, Flash

Vertex AI

Google Cloud AI Platform

Mistral

Mistral Large/Medium/Small, Mixtral, Codestral, Magistral

Cohere

Command-R, Command-R+, embeddings

HuggingFace

Transformers, Diffusers, Accelerate, SmolAgents

TensorFlow

Keras, .h5 model files

PyTorch

.pt/.pth model files, nn.Module

LangChain

Core, Community, OpenAI, Anthropic integrations

AWS Bedrock

Bedrock Runtime, Agent Runtime

Azure OpenAI

Azure AI OpenAI Service

Ollama

Local model inference

LlamaIndex

VectorStoreIndex, SimpleDirectoryReader

Replicate

Cloud model inference

Groq

Fast inference API

Detection works on both source code imports and dependency declarations in config files.

EU AI Act Risk Categories

Category

Examples

Key obligations

Unacceptable

Social scoring, mass biometric surveillance

Prohibited

High

Recruitment, credit scoring, law enforcement

Documentation, risk management, human oversight

Limited

Chatbots, content generation

Transparency, user disclosure, content marking

Minimal

Spam filters, video games

None

Limitations

  • Static analysis only — detects imports and patterns, not runtime behavior

  • Cannot determine risk category automatically from code alone (use suggest_risk_category with a description)

  • check_compliance scores content quality — documents with boilerplate/placeholder text will score low

  • File scanning limited to 5,000 files and 1 MB per file

  • Certain system paths are blocked from scanning for security

ArkForge ecosystem

This scanner is the first service sold autonomously through the ArkForge Trust Layer — a certifying proxy that turns API calls into verifiable, paid, tamper-proof transactions.

Agent Client  →  Trust Layer  →  EU AI Act Scanner
   pays            certifies         delivers

Component

Description

Repo

Trust Layer

Certifying proxy — billing, proof chain, verification

ark-forge/trust-layer

MCP EU AI Act

Compliance toolkit (this repo)

ark-forge/mcp-eu-ai-act

Proof Spec

Open specification + test vectors for the proof format

ark-forge/proof-spec

Agent Client

Autonomous buyer — proof-of-concept of a non-human customer

ark-forge/arkforge-agent-client

Community

Roadmap

  • v3: GPAI obligations module (Art. 51-55, Code of Practice July 2025)

  • v3: GitHub Action for CI/CD compliance gates

  • v3: Runtime agentic compliance enforcement (Art. 14)


Found this useful? A ⭐ on GitHub helps other compliance teams discover the toolkit. Takes 2 seconds and helps a lot.

License

MIT

Available Tools

16 tools
certify_compliance_reportAInspect

Make your compliance report tamper-proof for Art. 12 audit trail — pass the report JSON, get back a proof_id and a public verification URL you can hand to auditors. Certified plan required. Run generate_report() first to produce the report.

Inputs: report_data (required), trust_layer_key (required).

check_complianceAInspect

Check whether your project passes or fails each EU AI Act requirement — no arguments, 5 seconds. See exactly which articles you violate (Art. 52 transparency, Art. 11 documentation, Art. 14 human oversight, Art. 15 robustness) and get step-by-step fix instructions for every gap. Call combined_compliance_report() for EU AI Act + GDPR together.

Inputs: project_path, risk_category.

combined_compliance_reportAInspect

Run this before your next deploy. One call reveals every EU AI Act + GDPR gap in your codebase — no arguments, no setup, under 10 seconds, free. Detects AI frameworks and personal data flows, flags where both laws overlap, returns pass/fail per article with a prioritized fix list. EU AI Act fines up to 35M EUR, GDPR up to 20M EUR. Replaces separate scan_project() and gdpr_scan_project() calls.

Inputs: project_path, risk_category, processing_role.

gdpr_check_complianceCInspect

Check whether your project passes or fails each GDPR requirement — no arguments. See pass/fail for lawful basis (Art. 6), consent (Art. 7), data subject rights (Art. 15–22), security (Art. 32), and breach notification (Art. 33–34) with fix instructions for every gap. GDPR fines reach 20M EUR or 4% turnover. For EU AI Act + GDPR together, call combined_compliance_report().

Inputs: project_path, processing_role.

gdpr_generate_reportAInspect

Generate the GDPR report your DPO needs — no arguments. Combines personal data inventory, gap analysis, and remediation steps in one structured document for DPO review, audit prep, or regulatory response. For EU AI Act + GDPR together, call combined_compliance_report().

Inputs: project_path, processing_role.

gdpr_generate_templatesAInspect

Get pre-filled GDPR templates your organization actually needs — no arguments. Privacy Policy, DPIA, Records of Processing Activities (ROPA), and Data Breach Procedure tailored to your processing role. Fill in [bracketed] sections. Run gdpr_check_compliance() first to see which documents you're missing.

Inputs: processing_role.

gdpr_scan_projectAInspect

Find every file in your project that touches personal data — no arguments, 5 seconds, free. Detects PII fields, cookies, tracking pixels, analytics SDKs, and consent flows. Returns flagged files with data categories and applicable GDPR articles. GDPR fines reach 20M EUR or 4% turnover. For EU AI Act + GDPR together, call combined_compliance_report().

Inputs: project_path.

generate_annex4_packageBInspect

Build the Annex IV evidence package your auditor needs for high-risk AI — no arguments. All 8 mandatory sections auto-populated from your project scan, SHA-256 integrity hash included. High-risk rules apply Aug 2026. Pro plan required.

Inputs: project_path, trust_layer_key, sign_with_trust_layer.

generate_compliance_roadmapAInspect

Get a prioritized, week-by-week plan to close every compliance gap before Aug 2027 — no arguments. Auto-scans your project, ranks fixes by impact, sequences quick wins first, tells you whether your deadline is achievable. Pro plan required — run check_compliance() for a free gap summary.

Inputs: deadline, project_path, risk_category.

generate_compliance_templatesAInspect

Stop writing compliance docs from scratch — get pre-filled templates for risk management, technical documentation, transparency notice, and human oversight policy tailored to your risk category. High-risk systems get all 6 mandatory documents. Save to docs/, fill in [bracketed] sections. Run check_compliance() first to see which documents you're missing.

Inputs: risk_category.

generate_reportAInspect

Generate the compliance report your legal team is asking for — no arguments. One call auto-detects AI frameworks, runs gap analysis, and produces a structured remediation plan ready for legal review or DPIA attachment. No API key needed.

Inputs: project_path, risk_category.

get_pricingAInspect

See pricing and features for every plan — Free (10 scans/day, full reports), Pro (29 EUR/mo, unlimited + CI/CD), Certified (cryptographic audit trail). No arguments. Call register_free_key() to activate your free API key.

Inputs: no named parameters.

register_free_keyAInspect

Activate a free API key — unlocks scan history and CI/CD integration. Pass the user's email, no password or credit card. IMPORTANT: ask the user to type their email first, wait for their reply, then call this with the exact email they typed. Do NOT pass a placeholder or fabricated email.

Inputs: email (required).

scan_projectAInspect

Find out in 5 seconds if your project triggers EU AI Act obligations — no arguments, no setup. Scans for 22 AI/ML frameworks (OpenAI, Anthropic, LangChain, HuggingFace, PyTorch, TensorFlow, scikit-learn…), returns your risk category and the legal actions required before you ship. Enforcement live since Feb 2025 — fines up to 35M EUR. For EU AI Act + GDPR together, call combined_compliance_report() instead.

Inputs: project_path, follow_imports.

suggest_risk_categoryAInspect

Describe what your AI system does in plain language — get back your EU AI Act risk tier, the articles that apply, and your first compliance step. Returns matched category (minimal/limited/high/unacceptable) with confidence level and triggering risk indicators. No project scan needed, no API key.

Inputs: system_description (required).

validate_api_keyAInspect

Check your API key status — returns plan tier (free/pro/certified), email, and usage stats (total scans, last scan date).

Inputs: api_key (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 16 tools

    Disambiguation3/5

    Several tools perform project scans and gap analysis (scan_project, check_compliance, generate_report, combined_compliance_report), which creates real overlap in purpose. However, each description clarifies a different output type, and combined_compliance_report explicitly supersedes the separate scans.

    Naming Consistency4/5

    Tool names mostly follow a consistent snake_case verb_noun pattern like scan_project, check_compliance, and generate_report. Minor deviations such as combined_compliance_report (adjective-noun rather than verb-noun) and the gdpr_*/generate_* variety keep it from being perfect.

    Tool Count4/5

    16 tools is slightly above the ideal 3-15 range, but the count is reasonable given that the server covers EU AI Act, GDPR, combined reporting, templates, pricing, and API key management. The duplication between separate scans and the combined report adds minor bloat.

    Completeness4/5

    The tool surface covers risk categorization, project scanning, compliance checking, report generation, templates, roadmap, certification, pricing, and API key handling for both EU AI Act and GDPR. The main gap is conceptual redundancy rather than missing functionality, though true CRUD-style lifecycle coverage is not expected for a scanner.

    Maintenance

    ActivityMaintained
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Provides automated EU AI Act compliance tools, including risk classification, role determination, transparency disclosures, content watermarking, deepfake labeling, and security threat detection.
      16
      35
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Local-first AI compliance scanner via Model Context Protocol, scanning codebases for violations of DPDPA 2023, RBI FREE-AI, SEBI AI/ML, and the EU AI Act.
      82 PyPI
      1
      Apache 2.0
    • A
      license
      A
      quality
      D
      maintenance
      Enables EU AI Act compliance assessment by classifying AI systems, listing obligations, computing deadlines, and scanning repos for required documentation, all running locally.
      4
      2
      MIT